The ensemble approaches build upon the decision tree model builder by
building many decision tress through sampling the training dataset in
various ways. The ada
boosting algorithm is deployed by
Rattle to provide its boosting model builder. With the default
settings a very reasonable model can be built. At a 60% caseload we
are recovering 98% of the cases that required adjustment and 98% of
Note in printing a tree how n=xxxx and xxxx is 50% of the total
number of training instances. This is because bag.frac=0.5. Maybe need
an option in the interface to control this?
Copyright © 2004-2010 Togaware Pty Ltd
Support further development through the purchase of the PDF version of the book.
The PDF version is a formatted comprehensive draft book (with over 800 pages).
Brought to you by Togaware. This page generated: Sunday, 22 August 2010